title: >-
neukit: automatic brain extraction and preoperative tumor segmentation from
MRI
colorFrom: indigo
colorTo: indigo
sdk: docker
app_port: 7860
emoji: 🧠
pinned: false
license: mit
app_file: app.py
neukit
Automatic brain extraction and preoperative tumor segmentation from MRI
neukit was developed by SINTEF Medical Image Analysis to accelerate medical AI research.
Brief intro
This web application enables users to test Raidionics, which is an open-source, free-to-use desktop application for pre- and postoperative central nervous system tumor segmentation and standardized reporting. The app only supports single volume input and only demonstrates the segmentation results of the Raidionics software, and thus is only meant for demonstration purposes.
For postoperative tumor segmentation, standardized reporting, and better functionality for performing analysis on full cohorts (batch mode), please, refer to the Raidionics software which is hosted here.
Demo
To access the live demo, click on the Hugging Face badge above. Below is a snapshot of the current state of the demo app.
Development
Docker
Alternatively, you can deploy the software locally. Note that this is only relevant for development purposes. Simply dockerize the app and run it:
docker build -t neukit .
docker run -it -p 7860:7860 neukit
Then open http://127.0.0.1:7860 in your favourite internet browser to view the demo.
Python
It is also possible to run the app locally without Docker. Just setup a virtual environment and run the app.
Note that the current working directory would need to be adjusted based on where neukit is located on disk.
git clone https://github.com/andreped/neukit.git
cd neukit/
virtualenv -ppython3 venv --clear
source venv/bin/activate
pip install -r requirements.txt
python app.py --cwd ./
Troubleshooting
Note that due to share=True being enabled by default when launching the app,
internet access is required for the app to be launched. This can disabled by setting
the argument to --share 0.
Citation
If you found the tool useful in your research, please, cite the corresponding software paper:
@misc{bouget2023raidionics,
title={Raidionics: an open software for pre- and postoperative central nervous system tumor segmentation and standardized reporting},
author={David Bouget and Demah Alsinan and Valeria Gaitan and Ragnhild Holden Helland and André Pedersen and Ole Solheim and Ingerid Reinertsen},
year={2023},
eprint={2305.14351},
archivePrefix={arXiv},
primaryClass={physics.med-ph}
}